CN110020862A - A kind of business risk appraisal procedure, device and computer readable storage medium - Google Patents
A kind of business risk appraisal procedure, device and computer readable storage medium Download PDFInfo
- Publication number
- CN110020862A CN110020862A CN201810022139.4A CN201810022139A CN110020862A CN 110020862 A CN110020862 A CN 110020862A CN 201810022139 A CN201810022139 A CN 201810022139A CN 110020862 A CN110020862 A CN 110020862A
- Authority
- CN
- China
- Prior art keywords
- status data
- user
- risk
- service environment
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Computer Security & Cryptography (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of business risk appraisal procedure, device and computer readable storage mediums, to improve the timeliness and accuracy of risk evaluation result according to the real-time status of user and behavior dynamic adjustment risk evaluation result.Business risk appraisal procedure, comprising: in the risk assessment request for receiving operation system submission, obtain service environment status data, the service environment status data includes real time business environmental status data and history service environmental status data；The service environment status data is pre-processed；It is determining so that accumulation returns parameter and reaches maximum optimal risk control strategy according to pretreated service environment status data and current business Reward Program；According to the risk class of the service environment status data and the optimal risk control Policy evaluation active user.
Description
Technical field
The present invention relates to data mining technology field more particularly to a kind of business risk appraisal procedures, device and computer
Readable storage medium storing program for executing.
Background technique
Background that this section is intended to provide an explanation of the embodiments of the present invention set forth in the claims or context.Herein
Description recognizes it is the prior art not because not being included in this section.
Internet finance refers to be realized in financing, payment and information by means of Internet technology, mobile communication technology
The emerging financial models of the business such as Jie.Data generation, data mining, data safety and search engine technique are internet finance
Powerful support.Social networks, e-commerce, Third-party payment, search engine etc. form huge data volume, cloud computing and row
Make it possible that big data is excavated for analysis theories, Technology On Data Encryption goes on smoothly secret protection and transaction payment, and searches
Index, which is held up, makes user be more easier to obtain information, and the development of these technologies significantly reduces the cost and risk of financial transaction, expands
The big boundary of financial service.
Similar with traditional financial, risk control is also one of the critical issue that internet financial technology needs to solve.It is existing
Technology carries out risk control and generally uses following several method: grey black list library, risk control inventory, the side such as fraud regulation engine
Formula.Wherein, grey black list library refer to judge user or device id whether in the list, if, directly refuse the user or
Equipment uses business.If risk control inventory refers to if the information such as user behavior, device attribute hit the information in inventory,
Relative users are labeled as high risk.Fraud regulation engine refers to if the information such as user behavior, device attribute meet a set pattern
Then condition is then labeled as high risk, such as a fixed threshold is arranged in a certain property parameters, is high risk greater than this thresholding.
Prior art most forms for using unalterable rules in practical applications, it is inflexible, can not with when
Between the factors such as variation, user behavior variation, network environment, market environment, state-of-art and be adjusted flexibly, and most rule
All it is then artificial by expertise setting, there is very big subjectivity.
Moreover, existing some risk evaluation models based on big data and machine learning method are spoken with data, well
Solve the problems, such as subjectivity, but existing model mostly uses historical data (such as the data for running 6 months before batch time) off-line training
Afterwards, trained cure parameter is deployed to existing network environment, since the data volume of the whole network user is excessively huge, is limited by calculating energy
The limitation of power, often through full dose user data is monthly executed it is offline run batch processing after, model is exported into result (such as user
Risk class) it stores in the database, then the real-time of service inquiry is met by the result in real-time interface inquiry database
Property demand.It can be seen that existing scheme one side processing speed is slower, processing delay is larger, short for whole network data then several small
When, the long then several days time, real-time risk evaluation result can not be provided when wind comments query interface to request.History collected
Data are divided into the performance phase and observation period of user again, and data are relatively older, this to be not enough to according to the off-line learning of historical data
The feature of active user's behavior is reacted, model running prediction of result accuracy is relatively low.Another aspect a very long time mould
Shape parameter configuration will not change, after general such model running 1 year or half a year, have accumulated after enough historical datas again from
Line training Optimized model is still not able to be configured according to the real-time behavior expression dynamic flexible of service environment, user, adjust at any time
Strategy, model timeliness are poor.
Summary of the invention
The embodiment of the invention provides a kind of business risk appraisal procedure, device and computer readable storage medium, to
According to the real-time status of user and behavior dynamic adjustment risk evaluation result, the timeliness of risk evaluation result and accurate is improved
Property.
In a first aspect, providing a kind of business risk appraisal procedure, comprising:
In the risk assessment request for receiving operation system submission, service environment status data, the business ring are obtained
Border status data includes real time business environmental status data and history service environmental status data；
The service environment status data is pre-processed；
It is determining so that accumulation return is joined according to pretreated service environment status data and current business Reward Program
Number reaches maximum optimal risk control strategy；
According to the risk class of the service environment status data and the optimal risk control Policy evaluation active user.
Optionally, according to the service environment status data and the optimal risk control Policy evaluation active user
After risk class, further includes:
For each movement for including in preset set of actions, parameter and the service condition are returned according to the accumulation
Data determine the probability that the movement is selected；
The maximum movement of select probability is the movement performed for this risk assessment request.
Optionally, determine that parameter is returned in the accumulation according to following formula:
Wherein:
α is learning rate, α ∈ [0,1)；
ΔQπ(st,at) it is that parameter update error function is returned in preset accumulation；
Qπ(st,at) it is that parameter is returned in current accumulation, the expectation of accumulation return parameter is defined as follows:
Wherein:
Qπ(s, initial value a) are preset value；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
γ is constant discount factor, γ ∈ (0,1)；
For service environment status data stReach state s under the action of acting at+1Transition probability；
R(st,at) it is r (st,at) expectation；
R (s, a)=L (s, a) (1- τ) e-u, in which:
(s is a) income obtained after passing through for customer service application, if do not passed through for customer service application, L to L
(s, a)=0；
τ has indicated whether fraud, τ ∈ { 0,1 }, if there is fraud, τ=1；Otherwise, τ=0；
μ is rate of violation；
π is risk control strategy.
Optionally, for each movement for including in preset set of actions, parameter and described is returned according to the accumulation
Service condition data determine the probability that the movement is selected, and specifically include:
For each movement for including in preset set of actions, determine that the movement is selected general according to following formula
Rate:
Wherein:
p(at|st) indicate the probability that the movement is selected；
T is temperature value, and T is reduced with the increase of the number of iterations；
A indicates the set of actions；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
Q(st,at) indicate to return parameter when the accumulation of front-wheel；
Q(st+1,at+1) indicate that parameter is returned in the accumulation of next round.
Optionally, the real time business environmental status data includes at least one of the following: User Status data, user behavior
Data and user use facility information；The history service environmental status data includes at least one of the following: user's history business
Behavioral data, user's history consumer behavior data, user's history status data, user's history use facility information and user identity
Characteristic attribute information.
Second aspect provides a kind of business risk assessment device, comprising:
Data acquisition module, for obtaining service environment shape in the risk assessment request for receiving operation system submission
State data, the service environment status data include real time business environmental status data and history service environmental status data；
Data processing module, for being pre-processed to the service environment status data；
On-line study proxy module, for returning letter according to pretreated service environment status data and current business
Number determination is so that accumulation return parameter reaches maximum optimal risk control strategy；
Risk evaluation module, for being worked as according to the service environment status data and the optimal risk control Policy evaluation
The risk class of preceding user.
Optionally, the business risk assesses device, further includes:
Action selection module, for being returned according to the accumulation for each movement for including in preset set of actions
Parameter and the service condition data determine the probability that the movement is selected；The maximum movement of select probability is for this risk
The performed movement of assessment request.
Optionally, the on-line study proxy module, for determining that parameter is returned in the accumulation according to following formula:
Wherein:
α is learning rate, α ∈ [0,1)；
ΔQπ(st,at) it is that parameter update error function is returned in preset accumulation；
Qπ(st,at) it is that parameter is returned in current accumulation, the expectation of accumulation return parameter is defined as follows:
Wherein:
Qπ(s, initial value a) are preset value；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
γ is constant discount factor, γ ∈ (0,1)；
For service environment status data stReach state s under the action of acting at+1Transition probability；
R(st,at) it is r (st,at) expectation；
R (s, a)=L (s, a) (1- τ) e-u, in which:
(s is a) income obtained after passing through for customer service application, if do not passed through for customer service application, L to L
(s, a)=0；
τ has indicated whether fraud, τ ∈ { 0,1 }, if there is fraud, τ=1；Otherwise, τ=0；
μ is rate of violation；
π is risk control set of strategies.
Optionally, the action selection module, specifically for pressing for each movement for including in preset set of actions
The probability that the movement is selected is determined according to following formula:
Wherein:
p(at|st) indicate the probability that the movement is selected；
T is temperature value, and T is reduced with the increase of the number of iterations；
A indicates the set of actions；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
Q(st,at) indicate to return parameter when the accumulation of front-wheel；
Q(st+1,at+1) indicate that parameter is returned in the accumulation of next round.
Optionally, the real time business environmental status data includes at least one of the following: User Status data, user behavior
Data and user use facility information；The history service environmental status data includes at least one of the following: user's history business
Behavioral data, user's history consumer behavior data, user's history status data, user's history use facility information and user identity
Characteristic attribute information.
The third aspect provides a kind of computing device, including at least one processing unit and at least one storage unit,
Wherein, the storage unit is stored with computer program, when described program is executed by the processing unit, so that the processing
Unit executes step described in any of the above-described method.
Fourth aspect provides a kind of computer readable storage medium, is stored with the computer that can be executed by computing device
Program, when described program is run on the computing device, so that the computing device executes step described in any of the above-described method.
In business risk appraisal procedure provided in an embodiment of the present invention, device and computer readable storage medium, by right
Real time business environmental status data and history service environmental status data are applied to business risk assessment simultaneously, can be according to business
Environmental status data and business report the current optimal risk control strategy of the real-time flexible configuration of function, due to service environment state
Data are adjusted according to the real time data dynamic of operation system, therefore, so that business risk assessment is more time-efficient, improve industry
The accuracy for risk evaluation result of being engaged in.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by written explanation
Specifically noted structure is achieved and obtained in book, claims and attached drawing.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the structural schematic diagram that business envelope provided in an embodiment of the present invention believes assessment system；
Fig. 2 is the implementation process diagram of business risk appraisal procedure in the embodiment of the present invention；
Fig. 3 is in the embodiment of the present invention, and business risk assesses the structural schematic diagram of device；
Fig. 4 is the structural schematic diagram according to the computing device of mode of the embodiment of the present invention.
Specific embodiment
In order to improve the timeliness and accuracy of business risk assessment, the embodiment of the invention provides a kind of business risks to comment
Estimate method, apparatus and computer readable storage medium.
Below in conjunction with Figure of description, preferred embodiment of the present invention will be described, it should be understood that described herein
Preferred embodiment only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention, and in the absence of conflict, this hair
The feature in embodiment and embodiment in bright can be combined with each other.
In the embodiment of the present invention, by being carried out to collected user behavior information, facility information, network environment information etc.
Real-time online study, provides risk control strategy according to learning outcome, which is used to assess the risk class of user, the risk
The movement that grade is exported as system apply in operation system, according to the behavior expression of user (such as promise breaking, fraud after
Situations such as) feedback function that constitutes acts in risk control policy learning, be used for on-line tuning risk control strategy, and provide
It acts next time.In this way, dynamic adjusts risk control strategy, so that the promise breaking and fraud of user by constantly on-line study
Risk is minimum, to find optimal risk control strategy.As shown in Figure 1, it is commented for business risk provided in an embodiment of the present invention
Estimate the structural schematic diagram of system, including data acquisition module, data processing module, on-line study proxy module and movement selection mould
Block.Wherein:
Data acquisition module: it is responsible for capturing service environmental status data, such as financial industry user identity attribute information, use
The behavioural informations such as family Transaction Information, user's abnormal operation/promise breaking/fraud, user's local environment information (including location information, net
Network environmental information), facility information used by a user etc..
Data processing module: it is responsible for pre-processing the data of data collecting module collected, including duplicate removal, cleaning, sky
Value processing, Data Dimensionality Reduction, pretreatment, which calculate, generates derivative field etc., and the data which processes are input to on-line study agency
Module.
On-line study proxy module: it is responsible for the service environment status data s acquired to the t+1 momentt+1And t moment executes
Return r (the s that operation system provides after movement at,at) learnt, iteration updates risk control set of strategiesRisk class is exported to action selection module, whereinWhen for t+1
Carve the strategy updated, such as application loan product number, same cell-phone number registration terminal equipment number etc..Pass through continuous " examination
It is wrong " it attempts, the final goal of on-line study agency is the optimal risk control strategy π that find under each state s, so that about
The optimization aim of accumulation return maximizes.
When it is implemented, the mathematic expectaion that can define accumulation return parameter is as follows:
Wherein:
γ is constant discount factor, γ ∈ (0,1)；It embodies the importance of the relatively current return of future returns, and γ is got over
It is small, illustrate that the following value back is smaller relative to intertexture currently back, R (st,at) it is r (st,at) mathematic expectaion,For service environment status data stReach state s under the action of acting at+1Transition probability.Service environment state
The optimal value Q of data s*(s, a) and corresponding optimal risk control strategy π*It can be by calculating Q*(s a) is obtained:Wherein, Q*(s, a) can be by as follows
Iteration obtains:Wherein:
α is learning rate, α ∈ [0,1)；
ΔQπ(st,at) it is that parameter update error function is returned in preset accumulation.The risk control of link is examined in allograph,
It only needs to be defined Reward Program as follows: r (s, a)=L (s, a) (1- τ) e-u, in which:
L (s, a) (such as offer loans the receipts of acquisition to the user by the income to obtain after passing through for customer service application
Benefit), if do not passed through (for example, refusal loan) for customer service application, L (s, a)=0；τ has indicated whether fraud, τ
∈ { 0,1 }, if there is fraud, τ=1, then returning r, (s a) is 0；Otherwise, τ=0；μ is rate of violation, and rate of violation gets over Gao Ze
Return r (s, it is a) smaller.If τ=0 and μ=0, take credit society bear interest L (s, a).
Therefore, on-line study agency is in each round iterative process according to the service environment status data adjustment currently obtained
Risk control strategy π, so that Qπ(s, it is a) maximum, the risk of fraud grade of user under current state is provided according to optimal policy, such as
High risk, low-risk etc..
Action selection module: the risk class for being provided according to on-line study proxy module provides movement decision, example
Such as, if batch loan criticizes loan limit and interest rate after borrowing etc., wherein any action for including in a set of actions, with repeatedly
The process in generation updates a.
Wherein, operation system can be business of consumer credit system, be responsible for accepting, borrowing preceding examine, in loan for customer service
Monitoring is pressed for payment of after borrowing, and safeguards the business datum on user and its periphery.
Service environment status data s, be defined as in the embodiment of the present invention user identity attribute information, customer transaction information,
The behavioural informations such as user's abnormal operation/promise breaking/fraud, user's local environment information (including location information, network environment information),
Facility information used by a user etc..
Whether movement a: criticizing loan, loan limit and interest rate after batch loan.
Return r (s, a): the profitable result after referring to operation system execution movement.
Based on this, the embodiment of the invention provides a kind of business risk appraisal procedures, as shown in Fig. 2, it is business risk
The implementation process diagram of appraisal procedure, may comprise steps of:
S21, receive operation system submission risk assessment request when, obtain service environment status data, the industry
Business environmental status data includes real time business environmental status data and history service environmental status data.
For example, user inputs the amount of the loan, selects loan period, mode of repayment in operation system application loan class business
Deng.Operation system submits business risk assessment request to business risk assessment system, to assess consumer's risk grade.
In the service environment status data of business risk assessment system data collecting module collected operation system, including it is real-time
Service environment status data and history service environmental status data.
Wherein, real time business environmental status data includes at least one of the following:
(1) User Status data: for example current marital status, children's situation, income, condition of assets, geographic location,
Residence/place of working, reference grade, credit scoring etc.；
(2) user behavior data: when for example the same day/1 hour nearly/nearly 6 hours users borrow or lend money application, credit amount, debt-credit
Between, cell-phone number login times, cell-phone number registration debt-credit using number, registration mobile phone number, loan product number of clicks, concern debt-credit
Name of product, current loan product page stay time etc.；
(3) user uses facility information: active user's using terminal IMEI number, user account are associated with pass with terminal device
System, current device IP address, current device access network mode, equipment brand, device type, equipment price etc..
History service environmental status data includes at least one of the following:
(1) user's history business conduct data: for example nearly 1 month/3 months/6 months/12 months users borrow or lend money application, borrow
Monetary allowance volume, debt-credit time, cell-phone number login times, cell-phone number registration debt-credit are clicked using number, registration mobile phone number, loan product
Number, concern loan product title, the payment per month amount of money, history refund number, the overdue number of history, the overdue number of days of history etc.；
(2) user's history consumer behavior data: for example monthly converse ARPU (every user's average income) value, the history moon set meal
The amount of money, monthly average consumption amount of money etc.；
(3) user's history status information: marital status, children's situation, income, condition of assets, historical geography position, history
Residence/place of working, reference grade, credit scoring etc.；
(4) user's history uses facility information: (international mobile device is known by the used terminal brand of user, equipment IMEI
Other code) number, the cell-phone number device id (mark), common IP address, the common network access mode, device type, equipment that were associated with
Price, whether hit risk control inventory, whether doubtful mediation device etc..
(5) user identity characteristic attribute information: gender, age, user BOSS (business operation support system) brand, user
Star, whether real name etc..
S22, the service environment status data is pre-processed.
The behaviour such as duplicate removal, cleaning, assignment, storage is carried out to above data in the data processing module of business risk assessment system
Make, for example, remove duplicate data item, delete null value rate 80% or more dirty data sample, part sample null value is assigned
Value is handled, to different types of data item progress classification storage is for example stored by menology, per diem table stores, to the number of separate sources
According to Uniform data format etc.；
S23, according to pretreated service environment status data and current business Reward Program determination so that accumulating back
Report parameter reaches maximum optimal risk control strategy.
All variables are initialized in the on-line study proxy module of business risk assessment system, safeguard that a Q is (tired
Product return parameter) value table, a temperature T is associated with to each service environment status data ssAnd it is initialized as T0, at the beginning of learning rate α
Beginning turns to α0。
It should be noted that defining learning rate α and temperature T in the embodiment of the present invention and referring to the increase of the number of iterations in negative
Number rule decline, at the t+1 moment to service environment status data s, i.e. the real time business environmental status data that is obtained in step S21
Real-time online study is carried out with history service environmental status data and t moment (last round of) Reward Program r, i.e., is brought s and r into
Algorithmic function Qπ(st,at), it brings formula into and updates Qπ(st+1,at+1), it finds so that Qπ(st+1,at+1) maximum π, on-line study generation
It manages module and updates π value, according to the π value at current time, assess the consumer's risk grade, such as π is a series of threshold values, Yong Hutong
Application in one day is provided a loan, and number is greater than 3 or same user's difference account logging device number is greater than 3 or user's logging device IP
Situations such as user's marital status changes in address change is frequent or 1 month nearly appearance, meets any of the above policy condition, gives
Consumer's risk grade is high risk out, otherwise low-risk.
S24, according to the risk of the service environment status data and the optimal risk control Policy evaluation active user
Grade.
Wherein, in step S23, the accumulation return parameter can be determined according to following formula:
Wherein:
α is learning rate, α ∈ [0,1)；
ΔQπ(st,at) it is that parameter update error function is returned in preset accumulation；
Qπ(st,at) it is that parameter is returned in current accumulation, the expectation of accumulation return parameter is defined as follows:
Wherein:
Qπ(s, initial value a) are preset value；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
γ is constant discount factor, γ ∈ (0,1)；
For service environment status data stReach state s under the action of acting at+1Transition probability；
R(st,at) it is r (st,at) expectation；
R (s, a)=L (s, a) (1- τ) e-u, in which:
(s is a) income obtained after passing through for customer service application, if do not passed through for customer service application, L to L
(s, a)=0；
τ has indicated whether fraud, τ ∈ { 0,1 }, if there is fraud, τ=1；Otherwise, τ=0；
μ is rate of violation；
π is risk control set of strategies.
When it is implemented, on-line study process immediate stability can be made to get off by experience and restrained, however but it is faced with
Fall into the danger of local optimum；Richer and comprehensive experience will be obtained by more exploring new motion space, to reach more
Good optimization performance, but need to spend more learning times.In order to optimize the high efficiency and reliability that act selection, avoid
It falls into local optimum, in the embodiment of the present invention, the heuristic approach based on Boltzmann distribution can be used by such as lower probability entire
Motion space randomly chooses some movement a: for each movement for including in preset set of actions, being returned according to the accumulation
Parameter and the service condition data determine the probability that the movement is selected；The maximum movement of select probability is for this risk
The performed movement of assessment request.
Specifically, for each movement for including in preset set of actions, the movement can be determined according to following formula
The probability selected:
Wherein:
p(at|st) indicate the probability that the movement is selected；
T is temperature value, and T is reduced with the increase of the number of iterations；
A indicates the set of actions；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
Q(st,at) indicate to return parameter when the accumulation of front-wheel；
Q(st+1,at+1) indicate that parameter is returned in the accumulation of next round.
Wherein, temperature T is with Qπ(s, iterative process a) gradually decrease.
Based on this, in the embodiment of the present invention, for each movement for including in given set of actions, according in step S23
Obtained Qπ(st,at) value is updated to formulaIn, the corresponding probability of each movement is calculated,
According to the movement of the probability selection maximum probability, such as refusal loan, or agree to loan, 3000 yuan/5000 yuan etc. of amount, more
New learning rate α and temperature Ts, into next round iteration.
As known from the above, if epicycle iterative criterion user is low-risk, and higher rate is given, but is used in subsequent time
When business is applied at family again, according to user is current and the features such as the behavior of history (such as there are overdue behaviors, bull lend-borrow action
Deng Reward Program can change, and active user geographical location or IP address change, and there are risk of fraud), on-line study
The real-time adjustable strategies of agency's meeting, such as threshold level is turned up, to judge user for high risk, so that refusal be selected to provide a loan.Such as
Fruit epicycle iterative criterion user is low-risk, but gives lower amount, when subsequent time user applies for business again, according to
Currently and historical behavior feature (refunding on time, without overdue), on-line study agency understands real-time adjustable strategies, such as turns down door at family
Limit judges user for low-risk, and selection more preferably acts, such as improves amount, to keep income higher.
The intelligent method of on-line study is applied to risk control system by the embodiment of the present invention, according to the environment of operation system
The current optimal risk control strategy of the real-time flexible configuration of the information such as state and Reward Program, fraud hit rate more it is high more precisely, make
Risk control assessment and execute have more timeliness, solve the problems, such as existing system can not real-time perfoming risk assessment, reduce
Model running time delay, promotes risk assessment processing speed, really realizes grading in real time, and then promote forecasting accuracy, Yi Jimo
The timeliness of type promotes loan credit income so as to more efficient reduction risk of fraud.It is learned online using mass data
It practises, is spoken with data and dynamically adjust risk control strategy, avoid the subjectivity of anti-fraudulent policies.
Based on the same inventive concept, a kind of business risk assessment device is additionally provided in the embodiment of the present invention, due to above-mentioned
The principle that device solves the problems, such as is similar to business risk appraisal procedure, therefore the implementation of above-mentioned apparatus may refer to the reality of method
It applies, overlaps will not be repeated.
As shown in figure 3, its structural schematic diagram for assessing device for business risk provided in an embodiment of the present invention, comprising:
Data acquisition module 31, for obtaining service environment in the risk assessment request for receiving operation system submission
Status data, the service environment status data include real time business environmental status data and history service environmental status data；
Data processing module 32, for being pre-processed to the service environment status data；
On-line study proxy module 33, for being returned according to pretreated service environment status data and current business
Function is determining so that accumulation return parameter reaches maximum optimal risk control strategy；
Risk evaluation module 34, for according to the service environment status data and the optimal risk control Policy evaluation
The risk class of active user.
Optionally, the business risk assesses device, further includes:
Action selection module, for being returned according to the accumulation for each movement for including in preset set of actions
Parameter and the service condition data determine the probability that the movement is selected；The maximum movement of select probability is for this risk
The performed movement of assessment request.
Optionally, the on-line study proxy module, for determining that parameter is returned in the accumulation according to following formula:
Wherein:
α is learning rate, α ∈ [0,1)；
ΔQπ(st,at) it is that parameter update error function is returned in preset accumulation；
Qπ(st,at) it is that parameter is returned in current accumulation, the expectation of accumulation return parameter is defined as follows:
Wherein:
Qπ(s, initial value a) are preset value；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
γ is constant discount factor, γ ∈ (0,1)；
For service environment status data stReach state s under the action of acting at+1Transition probability；
R(st,at) it is r (st,at) expectation；
R (s, a)=L (s, a) (1- τ) e-u, in which:
(s is a) income obtained after passing through for customer service application, if do not passed through for customer service application, L to L
(s, a)=0；
τ has indicated whether fraud, τ ∈ { 0,1 }, if there is fraud, τ=1；Otherwise, τ=0；
μ is rate of violation；
π is risk control set of strategies.
Optionally, the action selection module, specifically for pressing for each movement for including in preset set of actions
The probability that the movement is selected is determined according to following formula:
Wherein:
p(at|st) indicate the probability that the movement is selected；
T is temperature value, and T is reduced with the increase of the number of iterations；
A indicates the set of actions；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
Q(st,at) indicate to return parameter when the accumulation of front-wheel；
Q(st+1,at+1) indicate that parameter is returned in the accumulation of next round.
Optionally, the real time business environmental status data includes at least one of the following: User Status data, user behavior
Data and user use facility information；The history service environmental status data includes at least one of the following: user's history business
Behavioral data, user's history consumer behavior data, user's history status data, user's history use facility information and user identity
Characteristic attribute information.
For convenience of description, above each section is divided by function describes respectively for each module (or unit).Certainly, exist
Implement to realize the function of each module (or unit) in same or multiple softwares or hardware when the present invention.
After the business risk appraisal procedure and device for describing exemplary embodiment of the invention, next, introducing
The computing device of another exemplary embodiment according to the present invention.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
In some possible embodiments, it is single can to include at least at least one processing for computing device according to the present invention
Member and at least one storage unit.Wherein, the storage unit is stored with program code, when said program code is described
When processing unit executes, so that the processing unit executes the exemplary implementations various according to the present invention of this specification foregoing description
Step in the business risk appraisal procedure of mode.For example, the processing unit can execute step S21 as shown in Figure 2,
In the risk assessment request for receiving operation system submission, service environment status data, the service environment state are obtained
Data include real time business environmental status data and history service environmental status data and step S22, to the service environment shape
State data are pre-processed and step S23, according to pretreated service environment status data and current business return letter
Number determination is so that accumulation return parameter reaches maximum optimal risk control strategy and step S24, according to the service environment
The risk class of status data and the optimal risk control Policy evaluation active user.
The computing device 40 of this embodiment according to the present invention is described referring to Fig. 4.The calculating dress that Fig. 4 is shown
Setting 40 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 4, computing device 40 is showed in the form of universal computing device.The component of computing device 40 may include
But be not limited to: at least one above-mentioned processing unit 41, at least one above-mentioned storage unit 42, the different system components of connection (including
Storage unit 42 and processing unit 41) bus 43.
Bus 43 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, processor or the local bus using any bus structures in a variety of bus structures.
Storage unit 42 may include the readable medium of form of volatile memory, such as random access memory (RAM)
421 and/or cache memory 422, it can further include read-only memory (ROM) 423.
Storage unit 42 can also include program/utility 425 with one group of (at least one) program module 424,
Such program module 424 includes but is not limited to: operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.
Computing device 40 can also be communicated with one or more external equipments 44 (such as keyboard, sensing equipment etc.), may be used also
Enable a user to the equipment interacted with computing device 40 communication with one or more, and/or with enable the computing device 40
Any equipment (such as router, modem etc.) communicated with one or more of the other calculating equipment communicates.This
Kind communication can be carried out by input/output (I/O) interface 45.Also, computing device 40 can also pass through network adapter 46
With one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.
As shown, network adapter 46 is communicated by bus 43 with other modules for computing device 40.It will be appreciated that though figure
In be not shown, can in conjunction with computing device 40 use other hardware and/or software module, including but not limited to: microcode, equipment
Driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system
Deng.
In some possible embodiments, the various aspects of business risk appraisal procedure provided by the invention can also be real
It is now a kind of form of program product comprising program code, it is described when described program product is run on a computing device
The exemplary embodiment party various according to the present invention that program code is used to that the computer equipment to be made to execute this specification foregoing description
Step in the business risk appraisal procedure of formula, for example, the computer equipment can execute step S21 as shown in Figure 2,
In the risk assessment request for receiving operation system submission, service environment status data, the service environment state are obtained
Data include real time business environmental status data and history service environmental status data and step S22, to the service environment shape
State data are pre-processed and step S23, according to pretreated service environment status data and current business return letter
Number determination is so that accumulation return parameter reaches maximum optimal risk control strategy and step S24, according to the service environment
The risk class of status data and the optimal risk control Policy evaluation active user.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example may be-but not limited to-electricity, magnetic, optical, electromagnetic, red
The system of outside line or semiconductor, device or device, or any above combination.The more specific example of readable storage medium storing program for executing
(non exhaustive list) includes: the electrical connection with one or more conducting wires, portable disc, hard disk, random access memory
(RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc
Read memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The program product for business risk assessment of embodiments of the present invention can be read-only using portable compact disc
Memory (CD-ROM) and including program code, and can run on the computing device.However, program product of the invention is unlimited
In this, in this document, readable storage medium storing program for executing can be any tangible medium for including or store program, which can be referred to
Enable execution system, device or device use or in connection.
Readable signal medium may include in a base band or as the data-signal that carrier wave a part is propagated, wherein carrying
Readable program code.The data-signal of this propagation can take various forms, including --- but being not limited to --- electromagnetism letter
Number, optical signal or above-mentioned any appropriate combination.Readable signal medium can also be other than readable storage medium storing program for executing it is any can
Read medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Program in connection.
The program code for including on readable medium can transmit with any suitable medium, including --- but being not limited to ---
Wirelessly, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind --- including local area network (LAN) or extensively
Domain net (WAN)-be connected to user calculating equipment, or, it may be connected to external computing device (such as utilize Internet service
Provider is connected by internet).
It should be noted that although being referred to several unit or sub-units of device in the above detailed description, this stroke
It point is only exemplary not enforceable.In fact, embodiment according to the present invention, it is above-described two or more
The feature and function of unit can embody in a unit.Conversely, the feature and function of an above-described unit can
It is to be embodied by multiple units with further division.
In addition, although describing the operation of the method for the present invention in the accompanying drawings with particular order, this do not require that or
Hint must execute these operations in this particular order, or have to carry out shown in whole operation be just able to achieve it is desired
As a result.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or by one
Step is decomposed into execution of multiple steps.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications can be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (12)
1. a kind of business risk appraisal procedure characterized by comprising
In the risk assessment request for receiving operation system submission, service environment status data, the service environment shape are obtained
State data include real time business environmental status data and history service environmental status data；
The service environment status data is pre-processed；
It is determining so that accumulation is returned parameter and reached according to pretreated service environment status data and current business Reward Program
To maximum optimal risk control strategy；
According to the risk class of the service environment status data and the optimal risk control Policy evaluation active user.
2. the method as described in claim 1, which is characterized in that according to the service environment status data and the optimal wind
After the risk class of dangerous control strategy assessment active user, further includes:
For each movement for including in preset set of actions, parameter and the service condition data are returned according to the accumulation
Determine the probability that the movement is selected；
The maximum movement of select probability is the movement performed for this risk assessment request.
3. the method as described in claim 1, which is characterized in that determine that parameter is returned in the accumulation according to following formula:
Wherein:
α is learning rate, α ∈ [0,1)；
ΔQπ(st,at) it is that parameter update error function is returned in preset accumulation；
Qπ(st,at) it is that parameter is returned in current accumulation, the expectation of accumulation return parameter is defined as follows:
Wherein:
Qπ(s, initial value a) are preset value；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
γ is constant discount factor, γ ∈ (0,1)；
For service environment status data stReach state s under the action of acting at+1Transition probability；
R(st,at) it is r (st,at) expectation；
R (s, a)=L (s, a) (1- τ) e-u, in which:
L (s is a) income obtained after passing through for customer service application, if do not passed through for customer service application, L (s,
A)=0；
τ has indicated whether fraud, τ ∈ { 0,1 }, if there is fraud, τ=1；Otherwise, τ=0；
μ is rate of violation；
π is risk control set of strategies.
4. method according to claim 2, which is characterized in that for each movement for including in preset set of actions, root
The probability that the movement is selected is determined according to the accumulation return parameter and the service condition data, is specifically included:
For each movement for including in preset set of actions, the probability that the movement is selected is determined according to following formula:
Wherein:
p(at|st) indicate the probability that the movement is selected；
T is temperature value, and T is reduced with the increase of the number of iterations；
A indicates the set of actions；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
Q(st,at) indicate to return parameter when the accumulation of front-wheel；
Q(st+1,at+1) indicate that parameter is returned in the accumulation of next round.
5. the method as described in Claims 1 to 4 any claim, which is characterized in that the real time business ambient condition number
According to including at least one of the following: User Status data, user behavior data and user using facility information；The history service ring
Border status data includes at least one of following: user's history business conduct data, user's history consumer behavior data, user's history
Status data, user's history use facility information and user identity characteristic attribute information.
6. a kind of business risk assesses device characterized by comprising
Data acquisition module, for obtaining service environment status number in the risk assessment request for receiving operation system submission
According to the service environment status data includes real time business environmental status data and history service environmental status data；
Data processing module, for being pre-processed to the service environment status data；
On-line study proxy module, for true according to pretreated service environment status data and current business Reward Program
It is fixed to reach maximum optimal risk control strategy so that accumulating and returning parameter；
Risk evaluation module, for currently being used according to the service environment status data and the optimal risk control Policy evaluation
The risk class at family.
7. device as claimed in claim 6, which is characterized in that further include:
Action selection module, for returning parameter according to the accumulation for each movement for including in preset set of actions
The probability that the movement is selected is determined with the service condition data；The maximum movement of select probability is for this risk assessment
The performed movement of request.
8. device as claimed in claim 6, which is characterized in that
The on-line study proxy module, for determining that parameter is returned in the accumulation according to following formula:
Wherein:
α is learning rate, α ∈ [0,1)；
ΔQπ(st,at) it is that parameter update error function is returned in preset accumulation；
Qπ(st,at) it is that parameter is returned in current accumulation, the expectation of accumulation return parameter is defined as follows:
Wherein:
Qπ(s, initial value a) are preset value；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
γ is constant discount factor, γ ∈ (0,1)；
For service environment status data stReach state s under the action of acting at+1Transition probability；
R(st,at) it is r (st,at) expectation；
R (s, a)=L (s, a) (1- τ) e-u, in which:
L (s is a) income obtained after passing through for customer service application, if do not passed through for customer service application, L (s,
A)=0；
τ has indicated whether fraud, τ ∈ { 0,1 }, if there is fraud, τ=1；Otherwise, τ=0；
μ is rate of violation；
π is risk control set of strategies.
9. device as claimed in claim 7, which is characterized in that
The action selection module, specifically for being directed to each movement in preset set of actions included, according to following formula
Determine the probability that the movement is selected:
Wherein:
p(at|st) indicate the probability that the movement is selected；
T is temperature value, and T is reduced with the increase of the number of iterations；
A indicates the set of actions；
S is service environment status data；
A is any action for including in set of actions；
T is when front-wheel identifies；
T+1 is next round mark；
Q(st,at) indicate to return parameter when the accumulation of front-wheel；
Q(st+1,at+1) indicate that parameter is returned in the accumulation of next round.
10. the device as described in claim 6~9 any claim, the real time business environmental status data includes following
At least one of: User Status data, user behavior data and user use facility information；The history service environmental status data
Include at least one of the following: user's history business conduct data, user's history consumer behavior data, user's history status data,
User's history uses facility information and user identity characteristic attribute information.
11. a kind of computing device, which is characterized in that including at least one processing unit and at least one storage unit,
In, the storage unit is stored with computer program, when described program is executed by the processing unit, so that the processing is single
First perform claim requires the step of 1~5 any claim the method.
12. a kind of computer readable storage medium, which is characterized in that it is stored with the computer journey that can be executed by computing device
Sequence, when described program is run on the computing device, so that the computing device perform claim requires 1~5 any the method
The step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810022139.4A CN110020862B (en) | 2018-01-10 | 2018-01-10 | Business risk assessment method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810022139.4A CN110020862B (en) | 2018-01-10 | 2018-01-10 | Business risk assessment method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110020862A true CN110020862A (en) | 2019-07-16 |
| CN110020862B CN110020862B (en) | 2021-10-29 |
Family
ID=67188055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810022139.4A Active CN110020862B (en) | 2018-01-10 | 2018-01-10 | Business risk assessment method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110020862B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827143A (en) * | 2019-11-08 | 2020-02-21 | 支付宝(杭州)信息技术有限公司 | Method, device and equipment for training credit scoring model |
| CN111131166A (en) * | 2019-11-28 | 2020-05-08 | 重庆小雨点小额贷款有限公司 | User behavior prejudging method and related equipment |
| CN111178701A (en) * | 2019-12-16 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Risk control method and device based on feature derivation technology and electronic equipment |
| CN111240912A (en) * | 2020-01-06 | 2020-06-05 | 重庆特斯联智慧科技股份有限公司 | Safety detection method and device based on intelligent access control equipment, storage medium and terminal |
| CN111339134A (en) * | 2020-02-11 | 2020-06-26 | 广州众赢科技有限公司 | Data query method and device |
| CN113282929A (en) * | 2021-06-29 | 2021-08-20 | 北京安天网络安全技术有限公司 | Behavior processing method, behavior processing device, behavior processing equipment and storage medium of mobile storage equipment |
| CN113450211A (en) * | 2021-08-31 | 2021-09-28 | 支付宝(杭州)信息技术有限公司 | User credit granting method, device, electronic equipment and storage medium |
| CN113627949A (en) * | 2021-08-24 | 2021-11-09 | 上海点融信息科技有限责任公司 | Credit limit adjusting method, device, equipment and storage medium |
| CN113807618A (en) * | 2021-11-19 | 2021-12-17 | 建元和光(北京)科技有限公司 | Method, device and equipment for hastening receipt of bad assets based on state machine |
| CN114841801A (en) * | 2022-07-04 | 2022-08-02 | 天津金城银行股份有限公司 | Credit wind control method and device based on user behavior characteristics |
| CN115630754A (en) * | 2022-12-19 | 2023-01-20 | 北京云驰未来科技有限公司 | Intelligent networking automobile information security prediction method, device, equipment and medium |
| CN116112203A (en) * | 2022-11-16 | 2023-05-12 | 广东一码通信科技有限公司 | Risk model-based network communication risk prediction method and device |
| CN117787707A (en) * | 2023-12-27 | 2024-03-29 | 国网江苏省电力有限公司信息通信分公司 | Instruction monitoring method and device, electronic equipment and medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236638A (en) * | 2008-02-20 | 2008-08-06 | 中国工商银行股份有限公司 | Web based bank card risk monitoring method and system |
| CN101662773A (en) * | 2008-08-29 | 2010-03-03 | 国际商业机器公司 | Method and equipment for realizing purpose of reducing communication deception risk by using computer |
| CN105894379A (en) * | 2016-03-30 | 2016-08-24 | 上海坤士合生信息科技有限公司 | System and method for generating financial product transaction strategy |
| CN105930214A (en) * | 2016-04-22 | 2016-09-07 | 广东石油化工学院 | Q-learning-based hybrid cloud job scheduling method |
| CN106845817A (en) * | 2017-01-11 | 2017-06-13 | 清华大学 | Online strengthening learns transaction system and method |
| CN106897918A (en) * | 2017-02-24 | 2017-06-27 | 上海易贷网金融信息服务有限公司 | A kind of hybrid machine learning credit scoring model construction method |
| CN106971338A (en) * | 2017-04-26 | 2017-07-21 | 北京趣拿软件科技有限公司 | The method and apparatus of data assessment |
| CN107230008A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | A kind of risk information output, risk information construction method and device |
| CN107481019A (en) * | 2017-07-28 | 2017-12-15 | 上海携程商务有限公司 | Order fraud recognition methods, system, storage medium and electronic equipment |
| CN107480895A (en) * | 2017-08-19 | 2017-12-15 | 中国标准化研究院 | A kind of reliable consumer goods methods of risk assessment based on Bayes enhancing study |
-
2018
- 2018-01-10 CN CN201810022139.4A patent/CN110020862B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236638A (en) * | 2008-02-20 | 2008-08-06 | 中国工商银行股份有限公司 | Web based bank card risk monitoring method and system |
| CN101662773A (en) * | 2008-08-29 | 2010-03-03 | 国际商业机器公司 | Method and equipment for realizing purpose of reducing communication deception risk by using computer |
| CN107230008A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | A kind of risk information output, risk information construction method and device |
| CN105894379A (en) * | 2016-03-30 | 2016-08-24 | 上海坤士合生信息科技有限公司 | System and method for generating financial product transaction strategy |
| CN105930214A (en) * | 2016-04-22 | 2016-09-07 | 广东石油化工学院 | Q-learning-based hybrid cloud job scheduling method |
| CN106845817A (en) * | 2017-01-11 | 2017-06-13 | 清华大学 | Online strengthening learns transaction system and method |
| CN106897918A (en) * | 2017-02-24 | 2017-06-27 | 上海易贷网金融信息服务有限公司 | A kind of hybrid machine learning credit scoring model construction method |
| CN106971338A (en) * | 2017-04-26 | 2017-07-21 | 北京趣拿软件科技有限公司 | The method and apparatus of data assessment |
| CN107481019A (en) * | 2017-07-28 | 2017-12-15 | 上海携程商务有限公司 | Order fraud recognition methods, system, storage medium and electronic equipment |
| CN107480895A (en) * | 2017-08-19 | 2017-12-15 | 中国标准化研究院 | A kind of reliable consumer goods methods of risk assessment based on Bayes enhancing study |
Non-Patent Citations (2)
| Title |
|---|
| P.GEIBEL等: "Risk-Sensitive Reinforcement Learning Applied to Control under Constraints", 《JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH》 * |
| 王磊: "社交数据驱动的P2P借贷风险评估模型", 《万方数据知识服务平台》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827143A (en) * | 2019-11-08 | 2020-02-21 | 支付宝(杭州)信息技术有限公司 | Method, device and equipment for training credit scoring model |
| CN111131166A (en) * | 2019-11-28 | 2020-05-08 | 重庆小雨点小额贷款有限公司 | User behavior prejudging method and related equipment |
| CN111178701A (en) * | 2019-12-16 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Risk control method and device based on feature derivation technology and electronic equipment |
| CN111178701B (en) * | 2019-12-16 | 2024-03-29 | 北京淇瑀信息科技有限公司 | Risk control method and device based on feature derivation technology and electronic equipment |
| CN111240912A (en) * | 2020-01-06 | 2020-06-05 | 重庆特斯联智慧科技股份有限公司 | Safety detection method and device based on intelligent access control equipment, storage medium and terminal |
| CN111339134B (en) * | 2020-02-11 | 2024-03-08 | 广州拉卡拉信息技术有限公司 | Data query method and device |
| CN111339134A (en) * | 2020-02-11 | 2020-06-26 | 广州众赢科技有限公司 | Data query method and device |
| CN113282929A (en) * | 2021-06-29 | 2021-08-20 | 北京安天网络安全技术有限公司 | Behavior processing method, behavior processing device, behavior processing equipment and storage medium of mobile storage equipment |
| CN113627949A (en) * | 2021-08-24 | 2021-11-09 | 上海点融信息科技有限责任公司 | Credit limit adjusting method, device, equipment and storage medium |
| CN113450211A (en) * | 2021-08-31 | 2021-09-28 | 支付宝(杭州)信息技术有限公司 | User credit granting method, device, electronic equipment and storage medium |
| CN113807618A (en) * | 2021-11-19 | 2021-12-17 | 建元和光(北京)科技有限公司 | Method, device and equipment for hastening receipt of bad assets based on state machine |
| CN114841801A (en) * | 2022-07-04 | 2022-08-02 | 天津金城银行股份有限公司 | Credit wind control method and device based on user behavior characteristics |
| CN116112203A (en) * | 2022-11-16 | 2023-05-12 | 广东一码通信科技有限公司 | Risk model-based network communication risk prediction method and device |
| CN116112203B (en) * | 2022-11-16 | 2023-07-28 | 广东一码通信科技有限公司 | Risk model-based network communication risk prediction method and device |
| CN115630754A (en) * | 2022-12-19 | 2023-01-20 | 北京云驰未来科技有限公司 | Intelligent networking automobile information security prediction method, device, equipment and medium |
| CN117787707A (en) * | 2023-12-27 | 2024-03-29 | 国网江苏省电力有限公司信息通信分公司 | Instruction monitoring method and device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110020862B (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110020862A (en) | A kind of business risk appraisal procedure, device and computer readable storage medium | |
| US20210365967A1 (en) | Systems and methods for interactive annuity product services using machine learning modeling | |
| CN107025509B (en) | Decision making system and method based on business model | |
| US20210118054A1 (en) | Resource exchange system | |
| US9792653B2 (en) | Recommender engine for collections treatment selection | |
| EP4214652A1 (en) | Computer-based systems, computing components and computing objects configured to implement dynamic outlier bias reduction in machine learning models | |
| KR20180117800A (en) | Method for providing asset portfolio recommendating service | |
| CN111080338B (en) | User data processing method and device, electronic equipment and storage medium | |
| CN110135691A (en) | Finance product methods of risk assessment, device, computer equipment and storage medium | |
| CN110705719A (en) | Method and apparatus for performing automatic machine learning | |
| KR102031312B1 (en) | Method for providing p2p fiancial platform based real estate loan service | |
| CN104321794A (en) | A system and method using multi-dimensional rating to determine an entity's future commercial viability | |
| KR102223844B1 (en) | Method for providing mentoring service connected investment, system and computer-readable medium recording the method | |
| Xue et al. | Incremental multiple kernel extreme learning machine and its application in Robo-advisors | |
| Xidonas et al. | Environmental corporate responsibility for investments evaluation: an alternative multi-objective programming model | |
| US20240220481A1 (en) | Method for identifying potential regulatory violations | |
| Skulimowski | A foresight support system to manage knowledge on information society evolution | |
| WO2019168632A1 (en) | Matching adopting users and contributing users for decentralized software localization | |
| CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
| US11983743B2 (en) | Training an artificial intelligence engine for generating models to provide targeted actions | |
| CN113313562B (en) | Product data processing method and device, computer equipment and storage medium | |
| US20210166318A1 (en) | Systems and methods for client profile-based sales decisions | |
| CN110599329B (en) | Credit evaluation method, credit evaluation device and electronic equipment | |
| CN113256404A (en) | Data processing method and device | |
| Verstraten et al. | The Case for Simple Simulation: Stochastic Market Simulation to Assess Renewable Business Cases |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |